机器学习基础⼊门_机器学习⼊门的5种⽅法
机器学习基础⼊门
Machine learning has taken off and it’s doing so with fury, bringing new insights to every single industry. If you want to be in demand, this is a skill that will put you in the front line. As intimidating as it may em, it’s surprisingly easy if you approach it the right way.
机器学习已经风起云涌，并且正在如此激昂，为每个⾏业带来了新见解。 如果您想获得需求，这是⼀种技巧，它将使您处于第⼀线。 尽管看起来令⼈⽣畏，但如果以正确的⽅式进⾏处理，这将⾮常容易。
Machine learning (ML) is a fascinating practice and field of study. It’s what allowed the introduction of lf-driven cars, of robots that can clean your hou, the navigation system of drones of all kinds, the recommendation system behind YouTube and Netflix, face recognition systems, hand written recognition, game playing, and lots more.
机器学习(ML)是⼀个有趣的实践和研究领域。 正是由于这些原因，才引⼊了⾃动驾驶汽车，可以打扫房屋的机器⼈，各种⽆⼈机的导航系统，YouTube和Netflix背后的推荐系统，⼈脸识别系统，⼿写识别，游戏等等。 。
And becau of its incredibly high value and somewhat cryptic nature, it’s an experti in very high demand that keeps expanding to different areas — which just five years ago would have emed inconceivable. Through this article, we’ll e different practical ways to approach it.
⽽且由于其难以置信的⾼价值和某种神秘的性质，它是⼀种在⾮常⾼的需求中的专业知识，并且不断扩展到不同的领域-仅在五年前这还简直不可思议。 通过本⽂，我们将看到不同的实践⽅法。
“对不起……但是什么是机器学习？” (“Pardon Me … but What is Machine Learning?”)
ML is a branch of artificial intelligence (AI). As Arthur Samuel — one of the pioneers in the field — put it, ML gives “computers the ability to learn without being explicitly programmed”. That is, instead of programming a computer (or robot) to do something, you give information and t the framework to let the system program itlf.
ML是⼈⼯智能(AI)的⼀个分⽀。 正如该领域的先驱之⼀Arthur Samuel所说的那样，ML使“计算机⽆需经过明确编程即可学习。” 也就是说，您⽆需提供计算机(或机器⼈)程序来执⾏某些操作，⽽是提供信息并设置框架以使系统⾃⾏编程。
Freaking fascinating? Yes, but we won’t get into the details of this emingly impossible thing here, but instead point you to the right places where you’ll be able to find that for yourlf.
让⼈着迷吗？ 是的，但是我们不会在这⾥详细介绍这看似不可能的事情，⽽是将您指向正确的地⽅，您可以⾃⼰找到这些地⽅。
开始之前，请注意 (Before Starting, a Word of Caution)
ML is something of an advanced practice, and you’ll need to have not only some foundations in computer sciences, but also be able to code in at least one programming language. Some popular programming languages for ML are Python, R, Java, C, and MATLAB, among others.
ML是⼀种⾼级实践，您不仅需要具备计算机科学的⼀些基础，⽽且还必须能够使⽤⾄少⼀种编程语⾔进⾏编码。 ML的⼀些流⾏编程语⾔是Python，R，Java，C和MATLAB等。
1.快速开始……真正地，不到⼗分钟 (1. Start Very Quickly … Like, Really, in Less than Ten Minutes)
Sometimes, and for some people, it’s better to just get hands on into something to have a first taste and develop an intuition of what this new art or skill is about, and then dig deeper into some specifics and details.
有时候，对于某些⼈来说，最好是先尝试⼀些东西，然后⾸先了解这种新艺术或技能的含义，然后再深⼊研究某些细节和细节。
Google’s with Josh Gordon is just that — a straightforward and practical approach to ML. Using the Python and libraries, Josh will walk you through very practical examples and down-to-earth explanations behind the very principles of ML.
⾕歌与乔什·⼽登 ( Josh Gordon )合作的就是这样-⼀种直接⽽实⽤的⽅法。 Josh使⽤Python 和库，将带您逐步了解⾮常实⽤的⽰例以及ML基本原理的扎实解释。
Here’s the first 7-minute video of the ries, introducing a supervid learning algorithm in Python —
in just six lines of code!:
这是该系列的前7分钟视频，仅⽤六⾏代码介绍了Python中的监督学习算法！ ：
The publishing schedule is somewhat irregular, with videos published every month or cond month, covering topics such as decision trees, feature lection, pipelines, classifiers: not bad at all for 6-to-8 minute videos that anyone with a little foundation in programming can follow.
发布时间表有些不规律，每个⽉或第⼆个⽉都会发布视频，内容涵盖决策树，功能选择，管道，分类器等主题：对于6到8分钟的视频来说⼀点都不差劲，任何有编程基础的⼈可以按照。
2.免费参加⼀流⼤学的课程 (2. Take Cours from Top-Notch Universities, for Free)
If you’re hungry for quality knowledge, you may have heard by now about , , , and , . We’re talking MOOCs, or .
如果你饿了质量知识，你可能现在听到有关 ， ， 和 ， 。 我们正在谈论MOOC，或 。
Let’s break it down quickly:
让我们快速分解⼀下：
massive: they have no vacancy limits, and can be accesd by as many people as desired.
庞⼤ ：他们没有职位空缺，可以由任意数量的⼈访问。
open: anyone can access them, regardless of their age and previous knowledge on the topic, and independently if they’re able to pay for a certification or not.
开放式 ：任何⼈都可以访问它们，⽽不论其年龄和对该主题的先前知识如何，并且⽆论他们是否能够⽀付认证费⽤，都可以独⽴访问。
束腰的危害online: all you need is a device connected to the Internet; even a mobile phone would do.
在线 ：您需要的只是连接到Internet的设备； 即使是⼿机也可以。
cour: the are actual cours with reading materials, practical exercis, and even deadlines.
课程 ：这些是实际课程，包括阅读材料，实践练习，甚⾄是截⽌⽇期。
Let’s e some cours you could start with.
让我们来看⼀些您可以开始的课程。
接近性
斯坦福⼤学的吴恩达机器学习 (Stanford’s Andrew Ng Machine Learning)
Stanford Prof. Ng is a leading rearcher on the field of artificial intelligence, and is the person who pretty much started the MOOC spark that would later turn into a fire of knowledge when he first put his online cour. The respon was overwhelming, with many thousands of people from all around the world taking the cour and discussing this topic. He later turned this cour into what it is today Courra, the leading provider of MOOCs.
斯坦福⼤学的Ng教授是⼈⼯智能领域的领先研究⼈员，并且是⼏乎开始产⽣MOOC⽕花的⼈，后来他⾸次上在线课程时就变成了知识之⽕。 对此React热烈，来⾃世界各地的数千⼈参加了该课程并讨论了这个主题。 后来，他将本课程转变为今天的MOOC的领先提供商Courra。
The cour is as fabulous as it is challenging. I remember having spent an hour or so just to read a 5-page assignment scope before I was able to grasp it. So unlike Josh Gordon’s ries, this is a little more on the academic side, but with a lot of practical knowledge and advice that will be very uful later on in your ML practices. But it is doable, and the amount of feedback on the forums is truly overwhelming. Mind you, it was among the first MOOCs I ever took, and one of the best.
优秀的作文文明交通图片这门课程既具有挑战性⼜很棒。 我记得花了⼀个⼩时左右的时间才阅读了5页的作业范围，然后才能
够掌握它。 因此，与乔什·⼽登(Josh Gordon)的系列不同，这在学术⽅⾯要多⼀些，但是具有许多实践知识和建议，这些知识和建议在以后的机器学习实践中将⾮常有⽤。 但这是可⾏的，并且在论坛上的反馈数量确实是压倒性的。 请注意，它是我参加过的第⼀批MOOC之⼀，也是最好的MOOC之⼀。
Cour details:
课程详情：
Approx. duration: 2–5 months
⼤约 持续时间 ：2–5个⽉
Difficulty: high
难度 ：⾼
Workload: mid-to-heavy
⼯作量 ：中到重
塞巴斯蒂安·特伦(Sebastian Thrun)的⼈⼯智能⼊门 (Sebastian Thrun’s Intro to Artificial Intelligence)
Also a professor and AI rearcher at Stanford (on ), co-founder of (the “mi-cret” R&D company behind of
Google’s lf-driven cars, ), Sebastian is also the founder of a mayor MOOC provider, Udacity. Along with Peter Norvig (Director of Rearch at Google), he put together the amazing .
塞巴斯蒂安(Sebastian) 还是斯坦福⼤学( )的教授兼AI研究员， (⾕歌⽆⼈驾驶汽车背后的“半秘密”研发公司， )的联合创始⼈。市长MOOC提供商Udacity。 与彼得·诺维格(Google研究总监)⼀起，他撰写了《惊⼈的 。
This is pretty much the foundation to all things ML. It’s a lot lighter than Andrew’s cour, with its content spread over more units to make it easier to digest, though it’s a long one.
这⼏乎是所有ML的基础。 它⽐安德鲁的课程要轻得多，它的内容分布在更多的单元上，以便于消化，尽管它很长。
Cour details:
课程详情：
霜是怎么形成的Approx. duration: 4 months
⼤约 持续时间 ：4个⽉
Difficulty: intermediate
难度 ：中级
Workload: light
⼯作量 ：轻
Caltec的Yar S. Abu-Mostafa从数据中学习 (Caltec’s Yar S. Abu-Mostafa Learning from Data)
湖北荆门市
Prof. Yar is another of the pioneers of putting quality learning material online, making available his Learning from Data , with all of its lectures, learning materials and exams, even before MOOCs were a thing. Later he would package the materials into .
Yar教授是将⾼质量的学习材料在线放置的另⼀位先驱，甚⾄在MOOC成为现实之前， 提供了他的“ 从数据 学习” 所有讲座，学习材料和考试。 后来，他将这些材料打包到 。
I took this one as well, and I can tell you that you’ll have to do some heavy lifting here. But if you’ve e
njoyed Andrew’s cour and are hungry for more foundations, this ems like a reasonable next step.
我也接受了这⼀点，我可以告诉你，您必须在这⾥做些繁重的⼯作。 但是，如果您喜欢安德鲁(Andrew)的课程并且渴望获得更多基础知识，那么下⼀步似乎是合理的。
Cour details:
课程详情：
Approx. duration: 4 months
⼤约 持续时间 ：4个⽉
Difficulty: very high
难度 ：很⾼
Workload: very heavy (10–20 hours per week)
⼯作量 ：⾮常重(每周10–20个⼩时)
其他Courra，edX和Udacity课程 (Other Courra, edX and Udacity Cours)
There’s a very extensive offering of ML and AI cours that you can take for free, not only at , , and , but at other MOOC providers as well, such as — though data science ems to be something of a niche for the three providers we’ve discusd.
您不仅可以在 ， 和 ，⽽且可以在其他MOOC提供商(例如免费提供⼤量的ML和AI课程，尽管数据科学似乎是⼀个利基市场我们讨论过的三个提供商。
3.获得部分价格的认证教育 (3. Get Certified Education, for a Fraction of the Price)
中国戏剧种类So far, we’ve talked free MOOCs. They’re awesome, and you don’t need to pay a cent to enroll in them and start learning. In the beginning, the providers ud to offer or , even . The programs, however, have been discontinued, so in most cas you won’t get a certificate or any type of credential that you could u to demonstrate your education to a potential employer, or even to another higher education institution.
到⽬前为⽌，我们已经讨论了免费的MOOC。 它们很棒，您⽆需花⼀分钱就可以开始学习。 最初，这些提供程序曾经提供或 ，甚⾄ 。 但是，这些程序已经终⽌，因此在⼤多数情况下，您不会获得可⽤于向潜在雇主甚⾄其他⾼等教育机构证明⾃⼰的学历的证书或任何类型的凭证。
This may not be a problem if you just want to learn for the sake of it, and even u this knowledge to leverage a successful career as a freelancer, as many professionals already do around the globe. But applying for work can be a different matter, and certs and degrees do ea the way in many cas, so let’s discuss them.
如果您只是想为此学习，甚⾄像全球许多专业⼈⼠所做的那样，甚⾄可以利⽤这些知识来发挥⾃由职业者的成功事业，那么这可能不是问题。 但是申请⼯作可能是另⼀回事，证书和学位确实可以简化很多情况，所以让我们讨论⼀下。
经过验证的课程 (Verified Cours)
A verified cour might be somewhere between $40–$200, depending on the cour and the institution. Basically, you pay a premium to get your identity and assignments verified (this is .) You can find more about and . You’ll find they both have a huge offering of ML and data-science–related verified cours, as you can e on this .
经验证的课程可能在$ 40- $ 200之间，具体取决于课程和机构。 基本上，您需要⽀付⼀定的费⽤才能使您的⾝份和作业得到验证(这是 。)您可以找到有关和 。 您会发现他们都提供⼤量与ML和数据科学相关的经过验证的课程，如您在所见。
Notice that, whether you pay or not, the contents and materials of the cour are exactly the same. What you get by paying is the certification that you actually took and pasd the cour.
高中同学聚会
请注意， ⽆论您是否付款，课程的内容和材料都是完全相同的。 通过付款获得的是您实际通过并通过该课程的证明。
Courra专业 (Courra Specializations)
Courra took the concept of verified cours a step forward by grouping some related cours and adding a capstone project to give you a .
Courra通过对⼀些相关的课程进⾏分组并添加⼀个顶点项⽬来为您提供 ，从⽽将经过验证的课程的概念向前推进了⼀步。
Some specializations of interest to us are:
我们感兴趣的⼀些专业是：
specialization cours institution
6UC San Diego
5deeplearning.ai
4University of Washington
5University of Minnesota
6University of Pennsylvania
(PGMs)3Stanford University
专业化培训班机构
6加州⼤学圣地亚哥分校
5deeplearning.ai
4华盛顿⼤学
5明尼苏达⼤学
6宾⼣法尼亚⼤学
(PGM)3斯坦福⼤学
Courra硕⼠学位 (Courra Master’s Degree)
Courra’s (MCS-DS) is an actual, official master’s degree issued by an accredited university. Topics in the program are heavily ML-related, and include:
Courra的 (MCS-DS)是由经认可的⼤学颁发的实际的官⽅硕⼠学位。 该程序中的主题与ML密切相关，包括：
data visualization
数据可视化
machine learning
机器学习
data mining
